{"id":"W2726670313","doi":"10.48550/arxiv.1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":470,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung; Deutsche Forschungsgemeinschaft; National Research Foundation; European Commission","keywords":"Computer science; Potential energy surface; Quantum; Grid; Convolutional neural network; Discretization; Deep learning; Chemical space; Filter (signal processing); Invariant (physics); Benchmark (surveying); Quantum dynamics; Differentiable function; Artificial intelligence; Theoretical computer science; Statistical physics; Molecule; Physics; Quantum mechanics; Chemistry; Mathematics; Computer vision; Geometry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003813899,0.0009328906,0.0005071104,0.0004537926,0.0003446509,0.0006588252,0.001723769,0.001366172,0.003733289],"category_scores_gemma":[0.001264959,0.0003828335,0.0005425649,0.0007051411,0.0005612075,0.001654004,0.0007851925,0.00156907,0.0009725643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00107357,"about_ca_system_score_gemma":0.001112492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008809656,"about_ca_topic_score_gemma":0.01538485,"domain_scores_codex":[0.9998591,0.0000230391,0.000005685585,0.00003454596,0.00005635438,0.0000212249],"domain_scores_gemma":[0.9998105,0.0000737567,0.00002453192,0.00003363643,0.00003889434,0.00001871935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001380663,0.00008492496,0.0007726388,0.00009986148,0.00007655258,0.00008561438,0.00002333417,0.8851188,0.00595318,0.02525515,0.01175086,0.07064097],"study_design_scores_gemma":[0.000003728567,0.000007945687,0.00004348559,0.000001853508,0.000002191197,0.000005377531,9.923118e-7,0.994659,0.0009852899,0.003586219,0.0007008695,0.000002980849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04698501,0.001003276,0.9338563,0.0008909634,0.0002291779,0.00008074932,0.001725522,0.008608322,0.006620753],"genre_scores_gemma":[0.6229951,0.0008756929,0.350004,0.0004767652,0.00009154665,0.0002102229,0.005558361,0.0006327408,0.01915562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008809656,"threshold_uncertainty_score":0.01751673,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1020130245770991,"score_gpt":0.2450478718179639,"score_spread":0.1430348472408648,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}